Seat belt wearing posture detection method and apparatus, device and storage medium

Abstract

Disclosed in the embodiments of the present invention are a seat belt wearing posture detection method and apparatus, a device and a storage medium. The method comprises: acquiring an image of a person in a vehicle and performing image segmentation on the image of the person in the vehicle, so as to obtain a corresponding seat belt segmentation result, the seat belt segmentation result comprising a diagonal seat belt region and a horizontal seat belt region; when the sum of the areas of the diagonal seat belt region and the horizontal seat belt region is greater than a preset area threshold, using a geometric method to draw a horizontal seat belt tangent line and a diagonal seat belt tangent line in the image of the person in the vehicle; and, according to the included angle between the horizontal seat belt tangent line and the diagonal seat belt tangent line, determining whether the seat belt wearing posture of the person in the vehicle is correct. The method determines whether a seat belt wearing posture is correct by using double mechanisms, i.e. the areas of seat belt regions and the included angle between seat belt tangent lines, thereby improving the detection accuracy and robustness and ensuring vehicle driving safety.

Description

A method, apparatus, device, and storage medium for detecting seatbelt wearing posture. Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to a method, apparatus, device, and storage medium for detecting seat belt wearing posture. Background Technology

[0002] Wearing a seatbelt while driving can provide protection for occupants in emergency situations and reduce the risk of injury in an accident.

[0003] In current technology, seatbelt wearing checks typically only determine if the seatbelt is fastened, lacking assessment of the wearing posture. Incorrect seatbelt wearing posture can reduce its protective effect during an accident, increasing the risk of injury to the driver and passengers. Therefore, it is necessary to check seatbelt wearing posture.

[0004] Summary of the Invention

[0005] This invention provides a method, apparatus, device, and storage medium for detecting seat belt wearing posture, thereby improving detection accuracy and robustness and ensuring vehicle driving safety.

[0006] According to one aspect of the present invention, a method for detecting seat belt wearing posture is provided, the method comprising:

[0007] Acquire images of occupants inside the vehicle, and perform image segmentation on the occupant images to obtain corresponding seat belt segmentation results; the seat belt segmentation results include diagonal seat belt regions and lateral seat belt regions;

[0008] When the sum of the areas of the diagonal seat belt region and the lateral seat belt region is greater than a preset area threshold, the lateral seat belt tangent and the diagonal seat belt tangent are drawn geometrically in the image of the occupants.

[0009] The angle between the tangent of the lateral seat belt and the tangent of the diagonal seat belt is used to determine whether the seat belt wearing posture of the occupants is correct.

[0010] Optionally, the lateral seatbelt tangent line and the diagonal seatbelt tangent line are drawn geometrically in the image of the occupants, including:

[0011] In the image of the occupants inside the vehicle, a pre-defined diagonal seat belt line is determined based on the pre-defined start and end points of the seat belt, and a first dot is determined on the perpendicular bisector of the pre-defined diagonal seat belt line.

[0012] In the image of the person in the vehicle, a transverse seat belt preset line is determined according to a preset end point of a seat belt, and a second circle point is determined on the transverse seat belt preset line;

[0013] A first concentric circle and a second concentric circle are respectively drawn with the first circle point and the second circle point as circle points, and an oblique seat belt tangent and a transverse seat belt tangent are respectively determined in tangent lines of the first concentric circle and the second concentric circle.

[0014] Optionally, the first circle point is determined on a midline of the oblique seat belt preset line, including:

[0015] The first circle point is determined on the midline of the oblique seat belt preset line, and the first circle point is a point with a distance from the oblique seat belt preset line being half a length of the oblique seat belt preset line;

[0016] The second circle point is determined on the transverse seat belt preset line, including:

[0017] The second circle point is determined on the transverse seat belt preset line, and the second circle point is a point with a distance from the oblique seat belt preset line being half a length of the oblique seat belt preset line.

[0018] Optionally, the oblique seat belt tangent and the transverse seat belt tangent are respectively determined in tangent lines of the first concentric circle and the second concentric circle, including:

[0019] In the first concentric circle, a first target circle is determined, which is located on a same side of the oblique seat belt region in the circle and does not contain a non-oblique seat belt region and has maximum contact with the oblique seat belt region;

[0020] A tangent line between the first target circle and the oblique seat belt region is drawn as the oblique seat belt tangent;

[0021] In the second concentric circle, a second target circle is determined, which is located on a same side of the transverse seat belt in the circle and does not contain a non-transverse seat belt region and has maximum contact with the transverse seat belt region;

[0022] A tangent line between the second target circle and the transverse seat belt region is drawn as the transverse seat belt tangent.

[0023] Optionally, whether a seat belt wearing posture of the person in the vehicle is correct is determined according to an included angle between the transverse seat belt tangent and the oblique seat belt tangent, including:

[0024] When the included angle between the transverse seat belt tangent and the oblique seat belt tangent is within a preset angle range, it is determined that the seat belt wearing posture of the person in the vehicle is correct;

[0025] Otherwise, it is determined that the seat belt wearing posture of the person in the vehicle is incorrect.

[0026] Optionally, the method further includes:

[0027] determining that the seat belt wearing posture of the occupant in the vehicle is incorrect when the sum of the areas of the oblique seat belt region and the transverse seat belt region is not greater than a preset area threshold.

[0028] Optionally, the method further comprises:

[0029] performing a seat belt wearing abnormality alarm when it is determined that the seat belt wearing posture of the occupant in the vehicle is incorrect.

[0030] According to another aspect of the present disclosure, there is provided a seat belt wearing posture detection device, comprising:

[0031] a seat belt segmentation result determination module configured to obtain an occupant image of a vehicle and perform image segmentation on the occupant image to obtain a corresponding seat belt segmentation result, wherein the seat belt segmentation result comprises an oblique seat belt region and a transverse seat belt region;

[0032] a seat belt tangent line drawing module configured to draw a transverse seat belt tangent line and an oblique seat belt tangent line in the occupant image by a geometric method when the sum of the areas of the oblique seat belt region and the transverse seat belt region is greater than a preset area threshold;

[0033] a seat belt wearing posture detection module configured to determine whether the seat belt wearing posture of the occupant in the vehicle is correct according to an included angle between the transverse seat belt tangent line and the oblique seat belt tangent line.

[0034] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0035] at least one processor; and

[0036] a memory communicatively connected to the at least one processor; wherein

[0037] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the seat belt wearing posture detection method according to any one of the embodiments of the present disclosure.

[0038] According to another aspect of the present disclosure, there is provided a computer readable storage medium storing computer instructions for enabling a processor to perform the seat belt wearing posture detection method according to any one of the embodiments of the present disclosure when executed by the processor.

[0039] According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program for enabling a processor to perform the seat belt wearing posture detection method according to any one of the embodiments of the present disclosure when executed by the processor.

[0040] The technical scheme of the embodiment of the present application obtains the in-vehicle personnel image of the vehicle, and performs image segmentation on the in-vehicle personnel image to obtain a corresponding seat belt segmentation result; the seat belt segmentation result includes a diagonal seat belt region and a horizontal seat belt region; when the sum of the areas of the diagonal seat belt region and the horizontal seat belt region is greater than a preset area threshold, a horizontal seat belt tangent and a diagonal seat belt tangent are drawn in the in-vehicle personnel image in a geometric manner; and whether the in-vehicle personnel seat belt wearing posture is correct is determined according to the included angle between the horizontal seat belt tangent and the diagonal seat belt tangent, thereby solving the problem of detecting the seat belt wearing posture, determining whether the seat belt wearing posture is correct through the double mechanisms of the area of the seat belt region and the included angle between the seat belt tangents, improving the detection accuracy and robustness, and ensuring the driving safety of the vehicle.

[0041] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0043] FIG. 1 is a flowchart of a seat belt wearing posture detection method according to an embodiment of the present application;

[0044] FIG. 2 is a schematic diagram of a seat belt segmentation result according to an embodiment of the present application;

[0045] FIG. 3 is a flowchart of a seat belt wearing posture detection method according to an embodiment of the present application;

[0046] FIG. 4 is a schematic diagram of a geometric dot positioning according to an embodiment of the present application;

[0047] FIG. 5 is a structural schematic diagram of a seat belt wearing posture detection device according to an embodiment of the present application;

[0048] FIG. 6 is a structural schematic diagram of an electronic device implementing the seat belt wearing posture detection method according to an embodiment of the present application. DETAILED DESCRIPTION

[0049] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work should belong to the protection scope of the present application.

[0050] It should be noted that the terms "first", "second" and the like in the description and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in other than the order illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a list of steps or units need not be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to such processes, methods, products or devices.

[0051] Embodiment one

[0052] FIG. 1 is a flowchart of a safety belt wearing posture detection method according to an embodiment of the present application. The embodiment can be applied to detecting the safety belt wearing posture of a person in a vehicle. The method can be executed by a safety belt wearing posture detection device, which can be implemented in the form of hardware and / or software. The safety belt wearing posture detection device can be configured in an electronic device such as a vehicle controller or a vehicle processor. As shown in FIG. 1, the method comprises the following steps.

[0053] In step 110, an image of a person in a vehicle is acquired, and image segmentation is performed on the image of the person in the vehicle to obtain a corresponding safety belt segmentation result.

[0054] In the embodiments of the present application, the in-vehicle personnel image can be an image of a driver or a passenger in the vehicle. The in-vehicle personnel image can include an image of the upper body and the abdominal region of the personnel. The in-vehicle personnel image can be captured by a camera, a video recorder or other imaging device. Specifically, to improve the accuracy of seat belt wearing detection, a camera with a resolution greater than a preset resolution can be used to capture real-time images of personnel inside the vehicle. For example, if the seat belt wearing situation of the driver or the front passenger is to be detected, the camera can be installed at the position of the instrument panel or the A-pillar of the vehicle. If the seat belt wearing situation of the rear passengers is to be detected, the camera can be installed at the position of the B-pillar or the interior roof of the vehicle. The specific number of cameras can be adjusted according to the actual seat belt wearing detection requirements.

[0055] To further improve the accuracy of seat belt wearing posture detection in different environments, a camera with adaptive exposure adjustment function can be used. The camera with adaptive exposure adjustment function can obtain clear in-vehicle personnel images under different lighting conditions, such as sunlight, shadow or night, thereby improving the accuracy of seat belt wearing posture detection.

[0056] Before image segmentation of the in-vehicle personnel image, the in-vehicle personnel image can also be preprocessed. The preprocessing operation includes but is not limited to image denoising, brightness adjustment and contrast enhancement. Through image preprocessing operation, the image quality can be improved, and a more accurate visual basis can be provided for seat belt wearing posture detection.

[0057] The image segmentation of the in-vehicle personnel image can be to segment the seat belt from the background in the image. Specifically, the seat belt segmentation result includes an oblique seat belt region and a horizontal seat belt region. For example, FIG. 2 is a seat belt segmentation result diagram provided by an embodiment of the present application. As shown in FIG. 2, the white seat belt region is the oblique seat belt region obtained by image segmentation, and the orange seat belt region is the horizontal seat belt region obtained by image segmentation.

[0058] The image segmentation method is not specifically limited in the embodiments of the present application. For example, the seat belt can be segmented from the image by a deep learning model or a traditional image processing method. For example, a semantic segmentation model such as hrnet can be trained to segment the seat belt region. The segmentation accuracy of the seat belt region can be pixel-level. By using a deep learning model for image segmentation, various personnel body types can be considered to improve the accuracy of seat belt segmentation, thereby improving the applicability and robustness of seat belt wearing posture detection.

[0059] Before the semantic segmentation model is trained, an in-vehicle personnel image of a vehicle can be collected, and image labeling can be performed to generate a semantic segmentation model training sample. The image labeling can be labeling the diagonal safety belt region and the transverse safety belt region in the in-vehicle personnel image. In the embodiment of the present application, through image labeling, advanced image processing or deep learning technology can be used to accurately segment and identify the two different parts of the diagonal safety belt and the transverse safety belt on the body of the personnel, and through accurate segmentation of the diagonal safety belt region and the transverse safety belt region, the basis for judging the safety belt wearing state and the posture correctness is provided.

[0060] Step 120, when the sum of the areas of the diagonal safety belt region and the transverse safety belt region is greater than the preset area threshold, drawing a transverse safety belt tangent and a diagonal safety belt tangent in the in-vehicle personnel image by a geometric method.

[0061] In the embodiment of the present application, the sum of the areas of the diagonal safety belt region and the transverse safety belt region can be calculated by a mathematical method. The specific area calculation method is not limited in the embodiment of the present application. The preset area threshold can be a fixed area value or an area ratio value. For example, the preset area threshold can be any value in the interval [300, 500], and the unit of the preset area threshold is square centimeter; optionally, the preset area threshold is 300, 350, 400, 450 or 500 square centimeters. Alternatively, the preset area threshold can be any value in the interval , and the meaning of the preset area threshold is the ratio of the sum of the areas to the area of the in-vehicle personnel image; optionally, the preset area threshold is

[0062] The transverse safety belt tangent and the diagonal safety belt tangent can be line segments representing the transverse safety belt region and the diagonal safety belt region, respectively. As shown in FIG. 2, the red line is the transverse safety belt tangent, and the green line is the diagonal safety belt tangent.

[0063] There are various ways to determine the transverse safety belt tangent and the oblique safety belt tangent. For example, the transverse safety belt tangent and the oblique safety belt tangent can be determined by geometrically fitting the transverse safety belt region and the oblique safety belt region. Alternatively, the transverse safety belt tangent can be obtained by connecting a first transverse point and a second transverse point in the transverse safety belt region in the image of the person in the vehicle. The first transverse point and the second transverse point are the start point and the end point of the transverse safety belt in the transverse safety belt region, respectively. The transverse safety belt tangent formed by the first transverse point and the second transverse point can be parallel to a horizontal line. The oblique safety belt tangent can be obtained by connecting a first oblique point and a second oblique point in the oblique safety belt region. The first oblique point and the second oblique point are the end point and the midpoint of the oblique safety belt in the oblique safety belt region, respectively. Alternatively, the transverse safety belt tangent and the oblique safety belt tangent can be determined by drawing concentric circles. The center of the concentric circles can be determined by geometric fitting.

[0064] In step 130, whether the safety belt wearing posture of the person in the vehicle is correct is determined according to the included angle between the transverse safety belt tangent and the oblique safety belt tangent.

[0065] In an optional embodiment of the present application, whether the safety belt wearing posture of the person in the vehicle is correct is determined according to the included angle between the transverse safety belt tangent and the oblique safety belt tangent, including: when the included angle between the transverse safety belt tangent and the oblique safety belt tangent is within a preset angle range, it is determined that the safety belt wearing posture of the person in the vehicle is correct; otherwise, it is determined that the safety belt wearing posture of the person in the vehicle is incorrect.

[0066] The preset angle range can be less than 90 degrees. Alternatively, the preset angle range can be greater than or equal to 20 degrees and less than 90 degrees. The geometric relationship between the included angle between the safety belt tangents can provide an intuitive and effective measurement for the safety belt wearing posture, and solve the problem of safety belt wearing posture detection. In the present application, the preset angle range can be used to detect the safety belt wearing posture of the person in the vehicle. When the safety belt wearing posture of the person in different positions in the vehicle is detected, the preset angle range can be different. For example, when the safety belt wearing posture of the person in the driver's seat or the front passenger's seat is detected, the preset angle range can be greater than or equal to 20 degrees and less than 90 degrees. For example, when the safety belt wearing posture of the person in the rear seat is detected, the preset angle range can be greater than or equal to 30 degrees and less than 90 degrees. By limiting the included angle between the transverse safety belt tangent and the oblique safety belt tangent by the preset angle range, the actual influence of different body types on the safety belt wearing can be considered, and reliable detection of the safety belt wearing posture can be achieved.

[0067] In an optional implementation of the embodiment of the present application, the method further comprises: determining that the seat belt wearing posture of the person in the vehicle is incorrect when the sum of the areas of the diagonal seat belt region and the transverse seat belt region is not greater than a preset area threshold. In the technical solution of the embodiment of the present application, the seat belt wearing posture detection result can be determined as a wearing posture error when the areas of the diagonal seat belt region and the transverse seat belt region are too small or do not exist, and specifically, the wearing posture error can be that the seat belt is not worn. The area judgment method can avoid excessive dependence on a complex image background, simplify the seat belt wearing posture detection method, and improve the seat belt wearing posture detection efficiency.

[0068] The technical solution of the embodiment of the present application obtains the image of the person in the vehicle, performs image segmentation on the image of the person in the vehicle, and obtains a corresponding seat belt segmentation result. The seat belt segmentation result includes a diagonal seat belt region and a transverse seat belt region. When the sum of the areas of the diagonal seat belt region and the transverse seat belt region is greater than a preset area threshold, the transverse seat belt tangent and the diagonal seat belt tangent are drawn in the image of the person in the vehicle through a geometric method. Whether the seat belt wearing posture of the person in the vehicle is correct is determined according to the included angle between the transverse seat belt tangent and the diagonal seat belt tangent, thereby solving the problem of detecting the seat belt wearing posture. The seat belt wearing posture is determined to be correct or incorrect through the double mechanisms of the areas of the seat belt regions and the included angle between the seat belt tangents, thereby improving the detection accuracy and robustness and ensuring the driving safety of the vehicle.

[0069] Embodiment Two

[0070] FIG. 3 is a flowchart of a seat belt wearing posture detection method according to Embodiment Two of the present application. The technical solution in this embodiment is a further refinement of the above technical solution, and can be combined with each optional solution in one or more of the above embodiments.

[0071] Specifically, in an optional implementation of the embodiment of the present application, the transverse seat belt tangent and the diagonal seat belt tangent are drawn in the image of the person in the vehicle through a geometric method, which comprises: determining a diagonal seat belt preset line in the image of the person in the vehicle according to a preset start and end point of the seat belt of the seat, and determining a first circular point on the perpendicular line of the diagonal seat belt preset line; determining a transverse seat belt preset line in the image of the person in the vehicle according to a preset end point of the seat belt of the seat, and determining a second circular point on the transverse seat belt preset line; drawing a first concentric circle and a second concentric circle with the first circular point and the second circular point as the circular points, respectively; and determining the diagonal seat belt tangent and the transverse seat belt tangent in the tangent lines of the first concentric circle and the second concentric circle, respectively.

[0072] As shown in FIG. 3, the method comprises:

[0073] Step 210, an in-vehicle personnel image of the vehicle is acquired, and image segmentation is performed on the in-vehicle personnel image to obtain a corresponding seat belt segmentation result.

[0074] In the seat belt segmentation result, a diagonal seat belt region and a horizontal seat belt region are included.

[0075] Step 220, when the sum of the areas of the diagonal seat belt region and the horizontal seat belt region is greater than a preset area threshold, a diagonal seat belt preset line is determined according to a preset start and end point of the seat belt in the in-vehicle personnel image, and a first circular point is determined on the median line of the diagonal seat belt preset line.

[0076] The preset start and end point of the seat belt can be a storage point of the seat belt and a buckle point of the seat belt, respectively. A line segment formed by the preset start and end point of the seat belt is the diagonal seat belt preset line. The first circular point can be determined on the median line of the diagonal seat belt preset line.

[0077] In an optional embodiment of the present application, in order to improve the detection reliability of the seat belt wearing posture, the first circular point is determined on the median line of the diagonal seat belt preset line, including: on the median line of the diagonal seat belt preset line, a point with a distance of half the length of the diagonal seat belt preset line from the diagonal seat belt preset line is determined as the first circular point.

[0078] FIG. 4 is a schematic diagram of a geometric method of circular point positioning according to an embodiment of the present application. As shown in FIG. 4, the red line segment is the diagonal seat belt preset line, and the green line perpendicular to the diagonal seat belt preset line is the median line. The yellow point on the median line is the first circular point.

[0079] Step 230, a horizontal seat belt preset line is determined according to a preset end point of the seat belt in the in-vehicle personnel image, and a second circular point is determined on the horizontal seat belt preset line.

[0080] The horizontal seat belt preset line is obtained by extending horizontally from the preset end point of the seat belt according to the direction of the seat belt. For example, when detecting the seat belt wearing posture of the driver, the horizontal seat belt preset line can be obtained by extending horizontally to the right from the preset end point of the seat belt. Or, when detecting the seat belt wearing posture of the co-driver, the horizontal seat belt preset line can be obtained by extending horizontally to the left from the preset end point of the seat belt. The second circular point can be selected on the horizontal seat belt preset line.

[0081] In an optional embodiment of the present application, in order to improve the detection accuracy of the seat belt wearing posture, the second circular point is determined on the horizontal seat belt preset line, including: on the horizontal seat belt preset line, a point with a distance of half the length of the diagonal seat belt preset line from the diagonal seat belt preset line is determined as the second circular point.

[0082] As shown in FIG. 4, the green line horizontally extending from the preset end point of the seat belt is the transverse seat belt preset line. The blue dot on the transverse seat belt preset line is the second circle dot.

[0083] In step 240, a first concentric circle and a second concentric circle are respectively drawn with the first circle dot and the second circle dot as the circle dots, and a diagonal seat belt tangent line and a transverse seat belt tangent line are respectively determined in the tangent lines of the first concentric circle and the second concentric circle.

[0084] Among the tangent lines of the first concentric circle, the tangent line capable of representing the diagonal seat belt region can be determined as the diagonal seat belt tangent line. Among the tangent lines of the second concentric circle, the tangent line capable of representing the transverse seat belt region can be determined as the transverse seat belt tangent line.

[0085] In order to improve the detection reliability of the seat belt wearing posture, in an optional implementation manner of the embodiment of the present application, the diagonal seat belt tangent line and the transverse seat belt tangent line are respectively determined in the tangent lines of the first concentric circle and the second concentric circle, including: in the first concentric circle, a first target circle is determined, which is on the same side of the diagonal seat belt region and does not contain a non-diagonal seat belt region, and which has the maximum contact with the diagonal seat belt region; a tangent line of the first target circle and the diagonal seat belt region is drawn as the diagonal seat belt tangent line; in the second concentric circle, a second target circle is determined, which is on the same side of the transverse seat belt and does not contain a non-transverse seat belt region, and which has the maximum contact with the transverse seat belt region; a tangent line of the second target circle and the transverse seat belt region is drawn as the transverse seat belt tangent line.

[0086] In the first concentric circle, a first target circle is determined, which is on the same side of the diagonal seat belt region and does not contain a non-diagonal seat belt region, and which has the maximum contact with the diagonal seat belt region. For example, in the seat belt wearing posture detection of the driver's seat, as shown in FIG. 2, in the first concentric circle, a circle on the lower right side of the circle does not contain the non-white seat belt region in FIG. 2, and has the maximum contact with the white seat belt region in FIG. 2, which is the first target circle. A tangent position of the first target circle and the diagonal seat belt region is a first tangent point. A tangent line of the first target circle at the first tangent point is the diagonal seat belt tangent line. For example, the diagonal seat belt tangent line is shown as the green line in FIG. 2.

[0087] In the second concentric circle, a second target circle is determined in the circle which is on the same side of the transverse safety belt and does not contain the non-transverse safety belt area and has the maximum contact with the transverse safety area. For example, in the safety belt wearing posture detection for the driver seat, as shown in FIG. 2, in the second concentric circle, the circle in the upper left side does not contain the non-orange safety belt area in FIG. 2 and has the maximum contact with the orange safety belt area in FIG. 2, that is, the second target circle. The position where the second target circle is tangent to the transverse safety belt area is the second tangent point. The tangent line of the second target circle is obtained by drawing a tangent line at the second tangent point. For example, the transverse safety belt tangent line is shown as a red line in FIG. 2.

[0088] By the cutting line determination method provided in the embodiments of the present application, a more reliable line representing the diagonal safety belt area and the transverse safety belt area can be obtained, and the detection reliability of the safety belt wearing posture is improved.

[0089] In step 250, when the included angle between the transverse safety belt tangent line and the diagonal safety belt tangent line is within a preset angle range, it is determined that the safety belt wearing posture of the person in the vehicle is correct; otherwise, it is determined that the safety belt wearing posture of the person in the vehicle is incorrect.

[0090] In step 260, when the sum of the areas of the diagonal safety belt area and the transverse safety belt area is not greater than a preset area threshold, it is determined that the safety belt wearing posture of the person in the vehicle is incorrect.

[0091] In step 270, when it is determined that the safety belt wearing posture of the person in the vehicle is incorrect, an abnormal safety belt wearing alarm is performed.

[0092] The abnormal alarm can be an audio and / or visual prompt alarm. In the embodiments of the present application, the abnormal alarm can be a real-time feedback mechanism, so as to accurately and timely prompt the person in the vehicle to wear the safety belt in a correct posture and ensure the driving safety.

[0093] The technical scheme of the embodiment of the present application obtains the in-vehicle personnel image of the vehicle, and performs image segmentation on the in-vehicle personnel image to obtain the corresponding seat belt segmentation result; when the sum of the areas of the diagonal seat belt region and the horizontal seat belt region is greater than a preset area threshold, in the in-vehicle personnel image, a diagonal seat belt preset line is determined according to the preset start and end points of the seat belt, and a first circular point is determined on the median line of the diagonal seat belt preset line; in the in-vehicle personnel image, a horizontal seat belt preset line is determined according to the preset end point of the seat belt, and a second circular point is determined on the horizontal seat belt preset line; a first concentric circle and a second concentric circle are drawn respectively with the first circular point and the second circular point as the circular points; and in the tangent line of the first concentric circle and the second concentric circle, the diagonal seat belt tangent line and the horizontal seat belt tangent line are determined respectively; when the included angle between the horizontal seat belt tangent line and the diagonal seat belt tangent line is within a preset angle range, it is determined that the in-vehicle personnel seat belt wearing posture is correct; otherwise, it is determined that the in-vehicle personnel seat belt wearing posture is incorrect; when the sum of the areas of the diagonal seat belt region and the horizontal seat belt region is not greater than the preset area threshold, it is determined that the in-vehicle personnel seat belt wearing posture is incorrect; when it is determined that the in-vehicle personnel seat belt wearing posture is incorrect, a seat belt wearing abnormality alarm is performed, thereby solving the detection problem of the seat belt wearing posture, determining whether the seat belt wearing posture is correct through the double mechanisms of the area of the seat belt region and the included angle between the seat belt tangent lines, improving the detection accuracy and robustness, and ensuring the driving safety of the vehicle; through image processing and computer vision technology, the intelligent level of seat belt detection is improved, the dependence on manual inspection is reduced, and at the same time, a higher-level safety feature tool is provided for intelligent automobile system integration, which can promote the progress of intelligent automobile technology; through the real-time feedback mechanism, the vehicle safety performance can be enhanced, and the driving experience can be improved; in addition, the method is not limited to seat belt detection of specific vehicle models, brands and specific positions, and has wide applicability and promotion value.

[0094] In the technical scheme of the embodiment of the present application, the acquisition, storage and application of the personal information of the user (such as the in-vehicle personnel image) all comply with the relevant legal regulations and do not violate public order and good customs.

[0095] Embodiment three

[0096] FIG. 5 is a structural schematic diagram of a seat belt wearing posture detection device according to embodiment three of the present application. As shown in FIG. 5, the device includes a seat belt segmentation result determination module 510, a seat belt tangent line drawing module 520 and a seat belt wearing posture detection module 530. Among them:

[0097] The seat belt segmentation result determination module 510 is configured to obtain the in-vehicle personnel image of the vehicle, and perform image segmentation on the in-vehicle personnel image to obtain the corresponding seat belt segmentation result; the seat belt segmentation result includes a diagonal seat belt region and a horizontal seat belt region;

[0098] The safety belt tangent line drawing module 520 is configured to draw the transverse safety belt tangent line and the diagonal safety belt tangent line in the image of the person in the vehicle by geometric means when the sum of the areas of the diagonal safety belt region and the transverse safety belt region is greater than a preset area threshold.

[0099] The safety belt wearing posture detection module 530 is configured to determine whether the safety belt wearing posture of the person in the vehicle is correct according to the included angle between the transverse safety belt tangent line and the diagonal safety belt tangent line.

[0100] Optionally, the safety belt tangent line drawing module 520 comprises:

[0101] The first circle point determination unit is configured to determine a diagonal safety belt preset line according to a preset start and end point of the seat safety belt in the image of the person in the vehicle, and determine a first circle point on the midline of the diagonal safety belt preset line.

[0102] The second circle point determination unit is configured to determine a transverse safety belt preset line according to a preset end point of the seat safety belt in the image of the person in the vehicle, and determine a second circle point on the transverse safety belt preset line.

[0103] The safety belt tangent line drawing unit is configured to draw a first concentric circle and a second concentric circle respectively with the first circle point and the second circle point as circle points, and determine the diagonal safety belt tangent line and the transverse safety belt tangent line respectively in the tangent line of the first concentric circle and the second concentric circle.

[0104] Optionally, the first circle point determination unit comprises:

[0105] The first circle point determination subunit is configured to determine, on the midline of the diagonal safety belt preset line, a point with a distance from the diagonal safety belt preset line being half the length of the diagonal safety belt preset line as the first circle point.

[0106] The second circle point determination unit comprises:

[0107] The second circle point determination subunit is configured to determine, on the transverse safety belt preset line, a point with a distance from the diagonal safety belt preset line being half the length of the diagonal safety belt preset line as the second circle point.

[0108] Optionally, the safety belt tangent line drawing unit comprises:

[0109] The first target circle determination subunit is configured to determine, in the first concentric circle, a first target circle on the same side of the diagonal safety belt region that does not contain a non-diagonal safety belt region and has the maximum contact with the diagonal safety belt region.

[0110] The diagonal safety belt tangent line drawing subunit is configured to draw the tangent line of the first target circle and the diagonal safety belt region as the diagonal safety belt tangent line.

[0111] The second target circle determining sub-unit is configured to determine, in the second concentric circle, a second target circle that is in the same side position as the transverse safety belt and does not contain the non-transverse safety belt region and has the maximum contact with the transverse safety region.

[0112] The transverse safety belt tangent line drawing sub-unit is configured to draw a tangent line between the second target circle and the transverse safety belt region as the transverse safety belt tangent line.

[0113] Optionally, the safety belt wearing posture detection module 530 comprises:

[0114] The first safety belt wearing posture detection unit is configured to determine that the safety belt wearing posture of the person in the vehicle is correct when the included angle between the transverse safety belt tangent line and the diagonal safety belt tangent line is within a preset angle range; otherwise, it is determined that the safety belt wearing posture of the person in the vehicle is incorrect.

[0115] Optionally, the device further comprises:

[0116] The second safety belt wearing posture detection unit is configured to determine that the safety belt wearing posture of the person in the vehicle is incorrect when the sum of the areas of the diagonal safety belt region and the transverse safety belt region is not greater than a preset area threshold.

[0117] Optionally, the device comprises:

[0118] The abnormality alarm module is configured to perform safety belt wearing abnormality alarm when it is determined that the safety belt wearing posture of the person in the vehicle is incorrect.

[0119] The safety belt wearing posture detection device provided by the embodiment of the present application can execute the safety belt wearing posture detection method provided by any embodiment of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0120] Embodiment four

[0121] FIG. 6 shows a structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (such as headsets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0122] As shown in FIG. 6, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0123] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, a speaker, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0124] The processor 11 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the seat belt wearing posture detection method.

[0125] In some embodiments, the seat belt wearing posture detection method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the seat belt wearing posture detection method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the seat belt wearing posture detection method by any other appropriate means, such as by means of firmware.

[0126] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0127] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program

[0128] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0129] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0130] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0131] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0132] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0133] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above, but only by the scope of the appended claims.

Claims

1. A seat belt wearing posture detection method characterized by comprising: The method comprises the following steps: obtaining an in-vehicle personnel image of a vehicle, and performing image segmentation on the in-vehicle personnel image to obtain a corresponding seat belt segmentation result; the seat belt segmentation result includes an oblique seat belt region and a transverse seat belt region; when the sum of the areas of the oblique seat belt region and the transverse seat belt region is greater than a preset area threshold, drawing a transverse seat belt tangent and an oblique seat belt tangent in the in-vehicle personnel image by a geometric method; determining whether the in-vehicle personnel seat belt wearing posture is correct according to the included angle between the transverse seat belt tangent and the oblique seat belt tangent.

2. The method of claim 1, wherein, drawing a transverse seat belt tangent and an oblique seat belt tangent in the in-vehicle personnel image by a geometric method comprises: in the in-vehicle personnel image, determining an oblique seat belt preset line according to a preset start and end point of the seat belt, and determining a first circular point on the perpendicular bisector of the oblique seat belt preset line; in the in-vehicle personnel image, determining a transverse seat belt preset line according to a preset end point of the seat belt, and determining a second circular point on the transverse seat belt preset line; drawing a first concentric circle and a second concentric circle respectively with the first circular point and the second circular point as the circular points; and determining the oblique seat belt tangent and the transverse seat belt tangent respectively in the tangent line of the first concentric circle and the second concentric circle.

3. The method of claim 2, wherein: determining a first circular point on the perpendicular bisector of the oblique seat belt preset line comprises: determining a point on the perpendicular bisector of the oblique seat belt preset line that is a distance of half the length of the oblique seat belt preset line from the oblique seat belt preset line as the first circular point; determining a second circular point on the transverse seat belt preset line comprises: determining a point on the transverse seat belt preset line that is a distance of half the length of the oblique seat belt preset line from the oblique seat belt preset line as the second circular point.

4. The method of claim 3, wherein, determining the oblique seat belt tangent and the transverse seat belt tangent respectively in the tangent line of the first concentric circle and the second concentric circle comprises: in the first concentric circle, determining a first target circle in the same side position of the oblique seat belt region that does not contain a non-oblique seat belt region and has the maximum contact with the oblique safety region; drawing the tangent line of the first target circle and the oblique seat belt region as the oblique seat belt tangent; in the second concentric circle, determining a second target circle in the same side position of the transverse seat belt that does not contain a non-transverse seat belt region and has the maximum contact with the transverse safety region; drawing the tangent line of the second target circle and the transverse seat belt region as the transverse seat belt tangent.

5. The method of claim 1, wherein, determining whether the in-vehicle personnel seat belt wearing posture is correct according to the included angle between the transverse seat belt tangent and the oblique seat belt tangent comprises: when the included angle between the transverse seat belt tangent and the oblique seat belt tangent is within a preset angle range, determining that the in-vehicle personnel seat belt wearing posture is correct; otherwise, determining that the in-vehicle personnel seat belt wearing posture is incorrect.

6. The method of claim 1, wherein, Further comprising: when the sum of the areas of the oblique seat belt region and the transverse seat belt region is not greater than the preset area threshold, determining that the in-vehicle personnel seat belt wearing posture is incorrect.

7. The method of claim 6, wherein, Further comprising: When it is determined that the safety belt wearing posture of the person in the vehicle is incorrect, a safety belt wearing abnormality alarm is given.

8. A seat belt wearing posture detection device characterized by comprising: The method comprises the steps of: a safety belt segmentation result determination module is configured to acquire an image of a person in a vehicle and perform image segmentation on the image to obtain a corresponding safety belt segmentation result; the safety belt segmentation result comprises a diagonal safety belt region and a horizontal safety belt region; a safety belt tangent line drawing module is configured to draw a horizontal safety belt tangent line and a diagonal safety belt tangent line in the image of the person in the vehicle by a geometric method when the sum of the areas of the diagonal safety belt region and the horizontal safety belt region is greater than a preset area threshold; a safety belt wearing posture detection module is configured to determine whether the safety belt wearing posture of the person in the vehicle is correct according to the included angle between the horizontal safety belt tangent line and the diagonal safety belt tangent line.

9. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the safety belt wearing posture detection method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the safety belt wearing posture detection method of any one of claims 1-7 when executed.

Images